MAHESH KUMAR N

@srmrmp.edu.in

ASSISTANT PROFESSOR/ELECTRONICS AND COMMUNICATION ENGINEERING
SRM INSTITUTE OF SCIENCE AND TECHNOLOGY, RAMAPURAM

MAHESH KUMAR N


                  Download Compact PDF  
https://researchid.co/maheshkn

RESEARCH INTERESTS

WIRELESS COMMUNICATION, COGNITIVE RADIO, MACHINE LEARNING, DEEP LEARNING
9

Scopus Publications

Scopus Publications

  • SOLAR POWER BASED GRASS CUTTING AND PESTICIDE SPRAYING ROBOT
    Arthi. R, D.Manoj Kumar, Mahesh Kumar.N, Praveenkumar Babu
    Esic 2026 Proceedings 6th International Conference on Emerging Systems and Intelligent Computing, 2026
    This study details the design and development of a solar-powered robot for grass cutting and pesticide spraying, which combines renewable energy harvesting with autonomous agricultural functions. The system employs a high-efficiency photovoltaic panel, an energyoptimized power management unit, and ESP8266-based control architecture to execute dual functions: precise grass cutting and targeted pesticide application. The mechanical subsystem features a rotary cutting blade powered by a DC motor and a pump-based pesticide delivery system, with navigation and obstacle avoidance facilitated by ultrasonic sensing and Bluetooth-controlled operation. Experimental findings indicate that the robot attains a <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{3 2 - 4 0 \%}$</tex> decrease in energy consumption relative to battery-only systems and traverses a conventional <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{1 0 0} \mathbf{m}^{\mathbf{2}}$</tex> field area <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{2 8 \%}$</tex> more swiftly than manual operations. Moreover, precision spraying decreased chemical consumption by 22 %, underscoring the system's ecological and financial advantages. These findings confirm the robot's capacity to improve agricultural productivity, diminish human labor, and facilitate sustainable field maintenance using solar-powered automation.
  • IOT BASED REAL-TIME WIRELESS DATA ACQUISITION SYSTEM FOR VEHICLE
    D. Manoj Kumar, Arthi. R, Mahesh Kumar. N, Praveenkumar Babu
    Esic 2026 Proceedings 6th International Conference on Emerging Systems and Intelligent Computing, 2026
    The objective of research work was to propose an IOT-based Real-time Wireless Data Acquisition System for Smart Vehicles, designed to monitor and assess a vehicle's internal parameters for the purpose of detecting its condition. The Proposed system serves as a realtime vehicle health monitoring solution, capable of identifying actuator and sensor faults, whether they occur automatically or are induced by the vehicle's user. The outcome of the system offers real-time evaluation, enabling rapid condition screening and providing reliable information about the vehicle's overall health. The Measuring Parameters heating rate, engine oil level, fuel level, vehicle speed, tier pressure, and carbon monoxide levels. The vehicle user neglects regular vehicle maintenance can lead to safety risks and various operational issues, making it crucial to develop an embedded IOT system for continuous vehicle health assessment. With minimal detection latency, even in the presence of disturbances and uncertainties like natural calamities this IOT-based system excels in detecting and identifying actuator and sensor faults.
  • Spectrum Sensing in Cognitive Radio Using Multiple Antenna by Eliminating Phase Noise
    Mahesh Kumar N, Arthi R
    Ssrg International Journal of Electronics and Communication Engineering, 2025
    Efficient spectrum sensing is crucial in Cognitive Radio Networks (CRNs) to identify and utilize unoccupied frequency bands, unobtrusively for primary users. By providing spatial diversity, the use of multiple antennas can enhance spectrum sensing performance. The proposed work makes use of multiple antenna spectrum sensing with a Deep Q Network (DQN) model to ascertain the existence of an estimated signal. The presence of phase noise reduces the efficiency of spectrum sensing compared to other widely used methods. To overcome this, the proposed work adopts Jelly Fish Optimization (JFO), Single Candidate Optimization (SCO) and Sand cat swarm optimization algorithms with Multiple Antenna Spectrum Sensing DQN (MASSDQN) to decrease the phase noise and enhance the spectrum sensing. The experimental outcome demonstrates the superior performance of the sand cat swarm optimization technique in multiple antenna spectrum sensing and optimize the phase noise for the secondary users to harness the spectrum effectively.
  • Applications of Television White Space–A Survey
    D. Manoj Kumar, R. Arthi, G. Vinoth Kumar, N. Mahesh Kumar
    Lecture Notes in Electrical Engineering, 2025
  • Optimizing Cognitive Radio Networks with Deep Learning-Based Semantic Spectrum Sensing
    Mahesh Kumar N, Arthi R
    Journal of Telecommunications and Information Technology, 2024
    Spectrum aggregation in 4G and 5G networks is a technique used to combine multiple frequency bands to boost communication performance. The cognitive radio feature improves the ability to combine spectrum in LTE and 5G environments by enabling dynamic spectrum sensing. Spectrum sensing is a major problem in spectrum aggregation due to the presence of various types of interference, such as noise. Phase noise is an issue due to its 1 MHz frequency offset experienced within 5G's 28 GHz operating band, with the distorted signal generating more spectrum sensing-related errors. To solve this problem, the proposed work suggests an optimized deep learning-based semantic spectrum sensing model using three sets of optimizers (ResNet-50, DeepLab V3 and sand cat) offering a high detection accuracy of 99.7% with the optimized training parameter of a high signal-to-noise ratio equaling 40 dB.
  • AI - Enhanced Wheelchair Solutions for Spinal Cord Injury (SCI) Individuals
    Mahesh Kumar N, J. Sruti, Pavan Kalyan P S, Sanjay Kumar A
    2024 International Conference on Signal Processing Computation Electronics Power and Telecommunication Iconscept 2024 Proceedings, 2024
    This paper is a design of a voice-controlled wheelchair which is well preferred for persons diagnosed with paraplegic and quadriplegic patients who can use voice commands to control and operate the wheelchair. Furthermore, an approach to sleep detection is developed through the utilization of OpenCV, enhancing the system's capability to identify periods of prolonged drowsiness indicative of potential sleep onset is also integrated. By harnessing the power of these technologies, we aim to enhance the independence, accessibility, and quality of life for individuals facing mobility challenges, ultimately paving the way for a more secure future. The Blynk app is used to develop a customized interface for controlling the wheelchair using voice commands. Users can create buttons within the Blynk app that correspond to specific commands, such as “move forward,” “turn left,” “turn right,” or “stop.” These commands can then be triggered by voice inputs detected by the app, allowing individuals to navigate the wheelchair hands-free. This Voice-Controlled AI Wheelchair project helps to enhance mobility for individuals with physical disabilities by developing a wheelchair that can be controlled using voice commands for navigation. This innovative assistive technology leverages voice recognition and artificial intelligence (AI) to provide users with intuitive and hands-free control over their mobility devices.
  • Block Chain Based Underwater Communication Using Li-Fi and Eliminating Noise Using Machine Learning
    Mahesh N, Arthi R, Krithika S
    Jordan Journal of Electrical Engineering, 2023
    Underwater medium is the most difficult medium for data communication while Electromagnetic waves, acoustic waves, and optical signals are some of the present modes of communication in water. Electromagnetic waves would suffer a significant loss, limiting them to short-range communication; optical waves on the other hand, have line-of-sight concerns. The proposed work employs a Light Fidelity (Li-Fi) data transmission technology in a water medium to address these issues. Visible light communication allows to use a wide range of frequencies to send messages, when compared to other transmission technologies, the data transfer rate is likewise relatively high. Electronic components and level converters are utilized to regulate flickering and communicate data on both the transmitter and receiver sides, when exposed to the outer environment, it will lose the signal due to noise. To help with noise level estimate and signal reconstruction, the proposed work employs a machine learning technique that uses an encrypted block chain approach to check for data loss and a weighted Long Short-Term Memory (LSTM) algorithm to predict data from a Neural Network. The proposed work concludes that block chain can be the best way for data transfer in terms of minimizing errors while maintaining high accuracy.
  • Deep Q Network-Based Spectrum Sensing for Cognitive Radio
    N. Mahesh Kumar, Phanikumar Polasi
    Lecture Notes in Electrical Engineering, 2022
  • Novel border alert management system using raspberry PI
    Journal of Advanced Research in Dynamical and Control Systems, 2019